Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    names of people or characters

    oai_token-act-pair · gpt-3.5-turbo

    the presence of empty or non-informative text segments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CPC
    -0.57
    âĶĢâĶĢ
    -0.56
     Oprah
    -0.53
     Appalach
    -0.53
     fragmented
    -0.52
     Californ
    -0.51
     equivalent
    -0.50
     underwater
    -0.50
     subsistence
    -0.50
     equivalents
    -0.49
    POSITIVE LOGITS
    kowski
    0.95
    ansky
    0.95
    inski
    0.93
    zinski
    0.92
    linger
    0.90
    itsch
    0.89
    insky
    0.88
    anski
    0.87
    atz
    0.87
    owski
    0.86
    Act Density 0.343%

    No Known Activations